Instructions to use travistest/gpt-oss-20b-json with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use travistest/gpt-oss-20b-json with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("travistest/gpt-oss-20b-json", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use travistest/gpt-oss-20b-json with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for travistest/gpt-oss-20b-json to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for travistest/gpt-oss-20b-json to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for travistest/gpt-oss-20b-json to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="travistest/gpt-oss-20b-json", max_seq_length=2048, )
Training in progress, step 2000
Browse files- README.md +2 -2
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -4,10 +4,10 @@ library_name: transformers
|
|
| 4 |
model_name: gpt-oss-20b-json
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- unsloth
|
| 8 |
-
- trl
|
| 9 |
- hf_jobs
|
|
|
|
| 10 |
- sft
|
|
|
|
| 11 |
licence: license
|
| 12 |
---
|
| 13 |
|
|
|
|
| 4 |
model_name: gpt-oss-20b-json
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
- hf_jobs
|
| 8 |
+
- trl
|
| 9 |
- sft
|
| 10 |
+
- unsloth
|
| 11 |
licence: license
|
| 12 |
---
|
| 13 |
|
adapter_config.json
CHANGED
|
@@ -33,12 +33,12 @@
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
-
"
|
|
|
|
|
|
|
| 37 |
"k_proj",
|
|
|
|
| 38 |
"q_proj",
|
| 39 |
-
"gate_proj",
|
| 40 |
-
"o_proj",
|
| 41 |
-
"down_proj",
|
| 42 |
"v_proj"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
|
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
+
"down_proj",
|
| 37 |
+
"o_proj",
|
| 38 |
+
"gate_proj",
|
| 39 |
"k_proj",
|
| 40 |
+
"up_proj",
|
| 41 |
"q_proj",
|
|
|
|
|
|
|
|
|
|
| 42 |
"v_proj"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 63726760
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15275cd168537868d00e83d52be911edf51c27b225f757d6c1a50872e8dee299
|
| 3 |
size 63726760
|
tokenizer_config.json
CHANGED
|
@@ -179,7 +179,7 @@
|
|
| 179 |
],
|
| 180 |
"model_max_length": 131072,
|
| 181 |
"pad_token": "<|reserved_200017|>",
|
| 182 |
-
"padding_side": "
|
| 183 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 184 |
"unk_token": null
|
| 185 |
}
|
|
|
|
| 179 |
],
|
| 180 |
"model_max_length": 131072,
|
| 181 |
"pad_token": "<|reserved_200017|>",
|
| 182 |
+
"padding_side": "right",
|
| 183 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 184 |
"unk_token": null
|
| 185 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6353
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6da02b023d2bf1d32d536155072665898f1960442de20e92aef1b1956948f433
|
| 3 |
size 6353
|